AI agents invoke prompt_user to trigger actions in Apple Notifier. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external UI operation on the user's Mac — displaying a modal dialog prompt — which is an interactive system-level action with effects that depend on the arguments passed (prompt text, options, etc.). It goes beyond a simple read/write because it causes a visible UI interruption and waits for user interaction.
From the tool's definition Display a dialog prompt to get user input
Documented attack patterns abuse exactly the kind of access prompt_user gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Notifier, and nothing reaches the server without passing your rules. This is the rule we recommend for prompt_user:
{
"version": "1",
"default": "deny",
"tools": {
"prompt_user": {
"limits": [
{
"counter": "prompt_user_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}prompt_user stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Display a dialog prompt to get user input. It is categorised as a Execute tool in the Apple Notifier MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Apple Notifier MCP server in PolicyLayer and add a rule for prompt_user: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Apple Notifier. Nothing to install.
prompt_user is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the prompt_user rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for prompt_user. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
prompt_user is provided by the Apple Notifier MCP server (turlockmike/apple-notifier-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Notifier, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Apple Notifier tools catalogued and risk-classified — across an index of 43,000+ MCP servers.